Brigham Young University (BYU) researchers say they have developed an algorithm that can accurately identify objects in images or video sequences without human calibration.
"With our algorithm, we give it a set of images and let the computer decide which features are important," says BYU's Dah-Jye Lee.
The algorithm can set its own parameters and it does not need to be reset each time a new object is to be recognized. Instead of telling the computer what to look at to distinguish between two objects, the researchers feed it a set of images and it learns on its own.
During testing, the researchers say the algorithm performed as well or better than other top object recognition algorithms to be published.
The researchers fed their object-recognition program four image datasets from CalTech and found 100-percent accurate recognition on every dataset. The results show the algorithm could be used for many applications, according to Lee.
"It's very comparable to other object-recognition algorithms for accuracy, but, we don't need humans to be involved," he says.
From BYU News (UT)
View Full Article
Abstracts Copyright © 2014 Information Inc., Bethesda, Maryland, USA
No entries found